Welcome to the first editorial of the new European Society of Cardiology (ESC) Working Group (WG) on e-Cardiology nucleus (2024-2026): Unlocking the future of cardiovascular care with AI and digital innovation.
Dear members of the ESC WG on e-Cardiology,
We are thrilled to introduce a collection of groundbreaking articles that embody the extraordinary potential of artificial intelligence (AI) and digital technologies to transform cardiovascular care. These studies offer insights into how AI-driven advancements in electrocardiography (ECG) and digital twin technology can deepen our understanding of heart health and enhance our clinical capabilities.
Our lead article, “Prediction of incident atrial fibrillation using deep learning, clinical models, and polygenic scores” by Jabbour et al., commented in detail by Panteleimon Pantelidis, reflects on the powerful implications of AI-driven analysis in uncovering hidden patterns within ECG data. This deep learning application opens a path for detecting atrial fibrillation with a higher predictive value than existing clinical and polygenic risk scores, potentially offering early intervention opportunities for at-risk patients.
The second feature, "Cardiovascular care with digital twin technology in the era of generative AI" by Thangaraj et al., explores the use virtual replicas of physical systems in cardiovascular health. Through generative AI, these digital twins can simulate patient-specific scenarios, offering a futuristic approach to precision medicine that could change how we predict, prevent, and treat cardiovascular conditions.
The third piece, "Advanced ECG heart age: a prognostic, explainable machine learning approach applicable to sinus and non-sinus rhythms" by Al-Falahi et al., introduces an innovative model for assessing the Heart Age gap, which has been shown to be associated with a higher prevalence of cardiovascular risk factors, hospitalizations, and mortality. Previously restricted to individuals in sinus rhythm, this model now utilizes standard 10-second, 12-lead ECGs and does not require P-wave information, enhancing its accessibility for broader clinical use. This expansion allows it to be applied to patients with atrial fibrillation and other conditions that result in non-quantifiable P-waves.
Finally, "AI-enabled ECG for mortality and cardiovascular risk estimation: a model development and validation study" by Sau et al., highlights the AI-ECG risk estimator (AIRE) platform. This innovative approach addresses the limitations of earlier AI-enabled ECG models, which provided survival probabilities at fixed time points rather than personalized risk trajectories over time. AIRE employs deep learning and a discrete-time survival model to generate patient-specific survival curves from single ECG readings, enabling predictions of both mortality risk and time-to-mortality. The study also identified biological pathways associated with increased risk, such as cardiac structural changes and genes linked to cardiac health, aging, and metabolic syndrome.
We invite you to dive into these forward-thinking articles as they exemplify the innovative spirit that will guide our board over the next term. Together, we look forward to advancing the field of e-Cardiology, fostering the integration of cutting-edge technologies, and ultimately improving patient outcomes in cardiovascular care.
On behalf of the entire ESC WG on e-Cardiology,
Monika Gawałko, MD, PhD,
ESC WG on e-Cardiology Communication Coordinator 2024-2026
Our mission: To reduce the burden of cardiovascular disease.